bert-3-epoch-sentiment
This model is a fine-tuned version of bert-base-uncased on the tweet_eval dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5772
- Accuracy: 0.6746
- Precision: 0.6776
- Recall: 0.6746
- Micro-avg-recall: 0.6746
- Micro-avg-precision: 0.6746
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Accuracy |
Precision |
Recall |
Micro-avg-recall |
Micro-avg-precision |
| 0.1114 |
1.0 |
2851 |
2.2420 |
0.6662 |
0.6705 |
0.6662 |
0.6662 |
0.6662 |
| 0.0949 |
2.0 |
5702 |
2.5923 |
0.6539 |
0.6676 |
0.6539 |
0.6539 |
0.6539 |
| 0.2172 |
3.0 |
8553 |
2.5772 |
0.6746 |
0.6776 |
0.6746 |
0.6746 |
0.6746 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
Author
Priyanka Balivada
